Journal of Non-Destructive Testing and Evaluation (JNDE)

Guideline for the Development of an NDE 4.0 Roadmap

Ripi Singh — 2023-12-07

‘What you don't know can't hurt you’ does NOT apply to Digital Transformation, as it is changing the value proposition from ‘competitive advantage’ to a ‘must do initiative’. NDE has seen revolutions somewhat parallel to industry. The current trends in cyber-physical technologies offer new possibilities wherein the inspectors can see the anomaly on a digital twin before they can see it on the conventional equipment, by fusing data from multiple sources and leveraging history captured in digital threads. To convert such a possibility into reality, organizations need a roadmap, particularly when the ecosystem is still evolving. Roadmaps are instrumental for guiding and thrusting sociocultural, economic, technological, and even political changes around the world.

This paper provides a guideline to the various stakeholders of the NDE ecosystem to develop a roadmap for NDE 4.0. Meaning this paper provides the necessary support regarding HOW to realize the value propositions of NDE 4.0, which have been developed in earlier publications [1,2,3,4,5].

AI for NDE 4.0 - How to get a Reliable and Trustworthy Result in Railway Based on the New Standards and Laws

D. Kanzler — 2023-12-07

The potential of artificial intelligence (AI) in our modern society is virtually boundless. However, alongside this potential, we are witnessing an increase in challenges and risks within the field. In Europe, these concerns have spurred discussions leading to the development of the AI Act, a European law designed to harness the potential of AI technology while safeguarding personal rights and security. This article will delve into the significance of AI in non-destructive evaluations (NDE) and (also) the necessary steps to establish reliable AI solutions. It's essential to note that this process should not be perceived solely as a regulatory requirement but as an opportunity to enhance value, ultimately enabling the creation of innovative maintenance concepts. As an illustrative example, we will explore the use of AI technologies in rail testing a part of the ongoing AIFRI project in Germany.

Adopting a Universal File Format for the Nondestructive Testing and Examination Industry

E. Peloquin — 2023-12-07

The NDT industry's transition to NDE 4.0 promises enhanced efficiency through digitalization, but it faces a significant bottleneck— the numerous incompatible file formats used by our equipment manufacturers. This article advocates the adoption of a universal open file format, namely, the .nde format. Utilizing HDF5 hardware description language, the .nde open file format offers increased data compatibility, accessibility, and archiving benefits, while its use of the JSON structure simplifies file management. In contrast to DICONDE, .nde proves flexible enough to generate DICONDE files, offering greater versatility.

The use of the open HDF5 language enables easy data viewing through multiple API options, facilitating customization to meet specific needs. Importantly, the .nde file format’s autonomy from proprietary software enables independent auditors and regulators to use custom software for unbiased data validation.

The adoption of a universal open file format unlocks numerous possibilities for the NDT industry, including integration into digital twining and inspection data management systems, fostering cooperation and knowledge sharing. It also empowers the industry to harness the potential of artificial intelligence (AI). By standardizing data formats, collaborative AI development and data sharing among equipment manufacturers become feasible, making the AI integration process more efficient.

While the vision of industry-wide collaboration may seem ambitious, this article contends that the adoption of the .nde open file format is the logical next step in the industry’s digitalization journey. Uniting key players to make all equipment compatible with .nde holds the promise of unleashing the industry's true potential and accelerating progress in the era of NDE 4.0.

CorrosionRADAR for Remote Monitoring of Corrosion Under Insulation (CUI) with Industrial IOT

Prafull Sharma — 2023-12-07

This paper explores the utilization of digital technologies, specifically the Industrial Internet of Things (IIOT), in the context of predictive Corrosion Management, focusing on a compelling case of corrosion occurring under insulation. It discusses the implementation of digitalization tools and presents real-world examples of their application in the field. By harnessing digital data collection and predictive algorithms based on factors like moisture levels and temperature, hidden corrosion issues such as Corrosion Under Insulation (CUI) can be effectively managed.

This approach involves leveraging gathered data to comprehensively oversee assets, identify high-risk areas, and plan inspections and maintenance proactively. The paper outlines a predictive methodology enabling asset owners to manage their assets both economically and safely by identifying and addressing risks beforehand. This technology integrates sensors to assess conditions under insulation and employs predictive modeling to swiftly estimate potential risks.

The paper delves into various use-cases and practical applications, demonstrating how employing sensors and industrial IoT can revolutionize the detection and prediction of corrosion in the field. This advancement holds significant promise for ensuring the integrity of assets plagued by concealed corrosion issues like CUI. The paper also presents the latest field case studies, bolstering confidence in this monitoring approach and contributing to the ongoing development of knowledge within the corrosion industry.

DPAI: In-Situ Process Intelligence using Data-Driven Simulation-Assisted-Physics Aware AI (DPAI) for Simulating Wave Dynamics

Thulsiram Gantala — 2023-12-07

AI models such as convolutional long short-term memory (ConvLSTM) recurrent neural network (RNN) have been shown here to have the capability to simulate ultrasonic wave propagation in the 2-D domain. This DPAI approach uses the Data-driven but simulation-assisted-Physics aware approach to utilizing AI networks. Our DPAI model comprises ConvLSTM with an encoder-decoder structure, which learns a representation of spatio-temporal features from the input sequence datasets. The DPAI model is trained with finite element (FE) time-domain simulation datasets consisting of distributed single and multi-point source excitation in the medium, reflection from the simple boundaries, and phased array steering. Here, this approach, called the DPAI model, is demonstrated for modelling multiple point sources to simulate forward wave propagation, reflection from the boundaries, and phased array beam steering ultrasound wave dynamics in a 2D plane. The trained DPAI model was found to be significantly faster in generating simulations for the time evolution of field values in the elastodynamic problem when compared to the conventional finite element explicit dynamic solvers.

AI-Driven CFRP Structure Evaluation: Deep Learning-Powered Automated Air-Coupled Ultrasonic Detection of Defect

Amitabha Datta — 2023-12-07

In this study, the successful experiments with air-coupled ultrasonic testing (ACUT) conducted on a 300 mm x 300 mm CFRP laminate, constructed from unidirectional Carbon Fibres, has been designed to simulate various types of damage during manufacturing, were presented as part of the experimental data. It was noted that the ACUT results exhibited strong correlations with the ground truth. To improve automated defect detection, a two-stage process was introduced. In the initial stage, C-Scan data acquired from the ACUT system was utilized. This data underwent meticulous analysis by a Convolutional Neural Network (CNN) image classifier, which categorized the images into two primary classes: defects and non-defects. Subsequently, defect instances underwent in-depth processing using Mask R-CNN, a technique that generated bounding boxes and segmentation masks for each defect zone within the images. The entire process was executed utilizing TensorFlow. The ultimate objective of this approach was to provide inspectors with the requisite tools to promptly and accurately discern and assess defects in composite materials, with the potential to substantially enhance the efficiency and precision of quality control processes in composite structures.